© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30681
    Prev
    Next
    INDEX
    Explanations

    instances of the word "crack" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    115
    +0.13
    0.8%
    164
    +0.13
    0.7%
    143
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.13
    0.02
    480
    +0.13
    0.01
    317
    +0.13
    0.01
    Negative Logits
     slightest
    -1.79
     precious
    -1.70
     yours
    -1.68
     certain
    -1.66
     LORD
    -1.53
     particular
    -1.45
     wealth
    -1.41
    Amazon
    -1.40
    aka
    -1.38
     much
    -1.38
    POSITIVE LOGITS
    gren
    1.94
    ingly
    1.87
    pot
    1.81
    inson
    1.80
    shots
    1.78
    strom
    1.74
    idable
    1.73
    pit
    1.67
    lei
    1.64
    starter
    1.61
    Activations Density 0.024%

    No Known Activations